{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NFFS5B6Z6ELNXT6R6M7R52QEVP","short_pith_number":"pith:NFFS5B6Z","schema_version":"1.0","canonical_sha256":"694b2e87d9f116dbcfd1f33f1eea04abef4d681a2961643188d39f941ee85e65","source":{"kind":"arxiv","id":"2403.13438","version":5},"attestation_state":"computed","paper":{"title":"SpatialPIN: Enhancing Spatial Reasoning Capabilities of Vision-Language Models through Prompting and Interacting 3D Priors","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrew Markham, Chenyang Ma, Kai Lu, Niki Trigoni, Ta-Ying Cheng","submitted_at":"2024-03-18T17:38:29Z","abstract_excerpt":"Current state-of-the-art spatial reasoning-enhanced VLMs are trained to excel at spatial visual question answering (VQA). However, we believe that higher-level 3D-aware tasks, such as articulating dynamic scene changes and motion planning, require a fundamental and explicit 3D understanding beyond current spatial VQA datasets. In this work, we present SpatialPIN, a framework designed to enhance the spatial reasoning capabilities of VLMs through prompting and interacting with priors from multiple 3D foundation models in a zero-shot, training-free manner. Extensive experiments demonstrate that o"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2403.13438","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-18T17:38:29Z","cross_cats_sorted":[],"title_canon_sha256":"2a8a7e2a311e420d9f13e06df90a04a4ee5341bb18336568e60341bd26a66c0a","abstract_canon_sha256":"7dd95608aadcabd178094f3ad260214411324100460f85ee18a0a32fbc23287b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:28:11.276009Z","signature_b64":"yXFq0oa1OyJ3FbmKWPENbKvZgR76jK9LDuVcZI0Pk2Fsgn+Dv+veSIancA63W/6z3TpH+j8vRXW5ZLQFz9XpCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"694b2e87d9f116dbcfd1f33f1eea04abef4d681a2961643188d39f941ee85e65","last_reissued_at":"2026-07-05T09:28:11.275556Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:28:11.275556Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SpatialPIN: Enhancing Spatial Reasoning Capabilities of Vision-Language Models through Prompting and Interacting 3D Priors","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrew Markham, Chenyang Ma, Kai Lu, Niki Trigoni, Ta-Ying Cheng","submitted_at":"2024-03-18T17:38:29Z","abstract_excerpt":"Current state-of-the-art spatial reasoning-enhanced VLMs are trained to excel at spatial visual question answering (VQA). However, we believe that higher-level 3D-aware tasks, such as articulating dynamic scene changes and motion planning, require a fundamental and explicit 3D understanding beyond current spatial VQA datasets. In this work, we present SpatialPIN, a framework designed to enhance the spatial reasoning capabilities of VLMs through prompting and interacting with priors from multiple 3D foundation models in a zero-shot, training-free manner. Extensive experiments demonstrate that o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.13438","kind":"arxiv","version":5},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2403.13438/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2403.13438","created_at":"2026-07-05T09:28:11.275613+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.13438v5","created_at":"2026-07-05T09:28:11.275613+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.13438","created_at":"2026-07-05T09:28:11.275613+00:00"},{"alias_kind":"pith_short_12","alias_value":"NFFS5B6Z6ELN","created_at":"2026-07-05T09:28:11.275613+00:00"},{"alias_kind":"pith_short_16","alias_value":"NFFS5B6Z6ELNXT6R","created_at":"2026-07-05T09:28:11.275613+00:00"},{"alias_kind":"pith_short_8","alias_value":"NFFS5B6Z","created_at":"2026-07-05T09:28:11.275613+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.13362","citing_title":"Enhancing Spatial Reasoning in Vision-Language Models via Chain-of-Thought Prompting and Reinforcement Learning","ref_index":36,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NFFS5B6Z6ELNXT6R6M7R52QEVP","json":"https://pith.science/pith/NFFS5B6Z6ELNXT6R6M7R52QEVP.json","graph_json":"https://pith.science/api/pith-number/NFFS5B6Z6ELNXT6R6M7R52QEVP/graph.json","events_json":"https://pith.science/api/pith-number/NFFS5B6Z6ELNXT6R6M7R52QEVP/events.json","paper":"https://pith.science/paper/NFFS5B6Z"},"agent_actions":{"view_html":"https://pith.science/pith/NFFS5B6Z6ELNXT6R6M7R52QEVP","download_json":"https://pith.science/pith/NFFS5B6Z6ELNXT6R6M7R52QEVP.json","view_paper":"https://pith.science/paper/NFFS5B6Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.13438&json=true","fetch_graph":"https://pith.science/api/pith-number/NFFS5B6Z6ELNXT6R6M7R52QEVP/graph.json","fetch_events":"https://pith.science/api/pith-number/NFFS5B6Z6ELNXT6R6M7R52QEVP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NFFS5B6Z6ELNXT6R6M7R52QEVP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NFFS5B6Z6ELNXT6R6M7R52QEVP/action/storage_attestation","attest_author":"https://pith.science/pith/NFFS5B6Z6ELNXT6R6M7R52QEVP/action/author_attestation","sign_citation":"https://pith.science/pith/NFFS5B6Z6ELNXT6R6M7R52QEVP/action/citation_signature","submit_replication":"https://pith.science/pith/NFFS5B6Z6ELNXT6R6M7R52QEVP/action/replication_record"}},"created_at":"2026-07-05T09:28:11.275613+00:00","updated_at":"2026-07-05T09:28:11.275613+00:00"}